CN112232845A - Method and device for predicting user behavior preference based on user position - Google Patents
Method and device for predicting user behavior preference based on user position Download PDFInfo
- Publication number
- CN112232845A CN112232845A CN201910635221.9A CN201910635221A CN112232845A CN 112232845 A CN112232845 A CN 112232845A CN 201910635221 A CN201910635221 A CN 201910635221A CN 112232845 A CN112232845 A CN 112232845A
- Authority
- CN
- China
- Prior art keywords
- target
- interest
- points
- point
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012216 screening Methods 0.000 claims abstract description 29
- 230000006399 behavior Effects 0.000 claims description 99
- 230000008094 contradictory effect Effects 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 13
- 239000012634 fragment Substances 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 8
- 238000012937 correction Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000004140 cleaning Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 101100343585 Arabidopsis thaliana LNG1 gene Proteins 0.000 description 1
- 102100038204 Large neutral amino acids transporter small subunit 1 Human genes 0.000 description 1
- 102100038235 Large neutral amino acids transporter small subunit 2 Human genes 0.000 description 1
- 108091006232 SLC7A5 Proteins 0.000 description 1
- 108091006238 SLC7A8 Proteins 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000000803 paradoxical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Abstract
The invention discloses a method and a device for predicting user behavior preference based on user position, wherein the method comprises the following steps: acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data; acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data; and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data. The method can combine personal position data and GIS data, is not limited to a specific vertical field, fully utilizes the GIS data to carry out diversified prediction, and gets rid of dependence on large-scale crowd data sets.
Description
Technical Field
The invention relates to the technical field of user behavior preference prediction, in particular to a method and a device for predicting user behavior preference based on user positions.
Background
With the rapid development of information technology and mobile internet, personalized services are perceived by more and more enterprises as a lean service, so more and more enterprises begin to try to acquire more information of customers through various ways, carry out more intensive research on the customers, try to predict the future requirements of the customers and infer the identity characteristics of the customers. The prediction of behavior preference and identity features is a hot spot in research, and is especially obvious today when data mining, machine learning, artificial intelligence and cloud computing are popular.
Most of the existing individual behavior preference and identity characteristic prediction methods are limited to prediction in a fixed vertical field, the starting point of prediction is a scene created in a certain vertical field, prediction for a certain demand is made on the basis of the scene, and all predictions need to have a specific scene, such as e-commerce and online reading. In a specific implementation algorithm, taking collaborative recommendation as an example, the prediction basis is a large-scale crowd data set, so that the problem of high quality of the crowd data set exists. The high quality is not only limited to the bulkiness of the crowd data set, but also has additional requirements for different specific implementations, such as data sparsity, although the crowd base number is large enough, the number of individuals generating behaviors is small, and most of the crowd data sets have the characteristic in reality, so the sparsity is also a problem widely faced by the algorithm.
Disclosure of Invention
In view of the above, the present invention has been made to provide a method and apparatus for predicting user behavior preferences based on user location that overcomes or at least partially solves the above-mentioned problems.
According to an aspect of the present invention, there is provided a method for predicting user behavior preference based on user location, comprising:
acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time and/or stay frequency corresponding to each position point contained in the personal position data;
acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data;
and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Optionally, the personal location data comprises: slice position data corresponding to a plurality of time slices, respectively;
then, according to the stay duration and/or the stay frequency corresponding to each location point included in the personal location data, screening at least one key location point corresponding to the target user includes:
determining the stay time of each position point contained in each fragment position data, and screening the position points with the stay time longer than a preset time threshold value as candidate position points in the fragment position data;
and determining the staying frequency of each candidate position point according to the occurrence frequency of each candidate position point in each fragment position data, and screening the candidate position points with the staying frequency not less than a preset frequency threshold value as key position points.
Optionally, predicting the user behavior preference of the target user according to the interest point corresponding to the target GIS data includes:
when a plurality of interest points corresponding to the target GIS data are available, judging whether each interest point is matched with a preset prediction target or not;
and determining the interest points matched with the preset prediction target as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, predicting the user behavior preference of the target user according to the interest point corresponding to the target GIS data includes:
when a plurality of interest points corresponding to the target GIS data are available, calculating the distance between each interest point and the key position point;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule or not;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, predicting the user behavior preference of the target user according to the interest point corresponding to the target GIS data includes:
when a plurality of interest points corresponding to the target GIS data exist, judging whether the attributes of the interest points meet preset constant station attribute rules or not;
if yes, the interest point is determined as a target interest point, and the user behavior preference of the target user is predicted according to the target interest point.
Optionally, predicting the user behavior preference of the target user according to the interest point corresponding to the target GIS data includes:
when a plurality of interest points corresponding to the target GIS data exist, judging whether mutually contradictory logics exist among the interest points;
if yes, screening the target interest points according to the distance between the interest points and the key position points and the weight corresponding to the interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, when there are a plurality of interest points corresponding to the target GIS data, before determining whether there is mutually contradictory logic between the interest points, the method further includes:
and presetting the weight corresponding to the interest point according to the pedestrian volume corresponding to the interest point and/or the distance between the interest point and the key position point.
According to an aspect of the present invention, there is provided an apparatus for predicting user behavior preference based on user location, comprising:
the key position point screening module is suitable for acquiring personal position data corresponding to a target user and screening at least one key position point corresponding to the target user according to the stay time length and/or the stay frequency corresponding to each position point contained in the personal position data;
the GIS data and interest point acquisition module is suitable for acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data;
and the behavior preference prediction module is suitable for predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Optionally, the personal location data comprises: slice position data corresponding to a plurality of time slices, respectively;
the key location point screening module is adapted to:
determining the stay time of each position point contained in each fragment position data, and screening the position points with the stay time longer than a preset time threshold value as candidate position points in the fragment position data;
and determining the staying frequency of each candidate position point according to the occurrence frequency of each candidate position point in each fragment position data, and screening the candidate position points with the staying frequency not less than a preset frequency threshold value as key position points.
Optionally, the behavior preference prediction module is adapted to:
when a plurality of interest points corresponding to the target GIS data are available, judging whether each interest point is matched with a preset prediction target or not;
and determining the interest points matched with the preset prediction target as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behavior preference prediction module is adapted to:
when a plurality of interest points corresponding to the target GIS data are available, calculating the distance between each interest point and the key position point;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule or not;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behavior preference prediction module is adapted to:
when a plurality of interest points corresponding to the target GIS data exist, judging whether the attributes of the interest points meet preset constant station attribute rules or not;
if yes, the interest point is determined as a target interest point, and the user behavior preference of the target user is predicted according to the target interest point.
Optionally, the behavior preference prediction module is adapted to:
when a plurality of interest points corresponding to the target GIS data exist, judging whether mutually contradictory logics exist among the interest points;
if yes, screening the target interest points according to the distance between the interest points and the key position points and the weight corresponding to the interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behavior preference prediction module is adapted to:
and presetting the weight corresponding to the interest point according to the pedestrian volume corresponding to the interest point and/or the distance between the interest point and the key position point.
According to still another aspect of the present invention, there is provided an electronic apparatus including: the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the method for predicting the user behavior preference based on the user position.
According to yet another aspect of the present invention, a computer storage medium is provided, where at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to the method for predicting user behavior preference based on user location as described above.
In summary, the invention discloses a method and a device for predicting user behavior preference based on user position. Firstly, personal position data corresponding to a target user is obtained, and at least one key position point corresponding to the target user is screened according to the stay time length and/or the stay frequency corresponding to each position point contained in the personal position data. Then, target GIS data corresponding to the at least one key location point and interest points corresponding to the target GIS data are acquired. And finally, predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data. The method can combine personal position data and GIS data, fully utilizes the GIS data to carry out diversified prediction, is not limited to a specific vertical field, and gets rid of dependence on large-scale crowd data sets.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow diagram illustrating a method for predicting user behavior preferences based on user location according to one embodiment;
FIG. 2 is a flow diagram illustrating a method for predicting user behavior preferences based on user location in accordance with a second embodiment;
FIG. 3 is a block diagram of an apparatus for predicting user behavior preferences based on user location according to a third embodiment;
FIG. 4 is a schematic diagram of an electronic device according to an embodiment of the invention;
FIG. 5 illustrates a user location track abstraction diagram;
FIG. 6 shows a coincidence trajectory key location point refinement diagram;
FIG. 7 shows a shortest distance matching diagram;
fig. 8 shows a mutually contradictory determination correction processing flowchart.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
Fig. 1 shows a flowchart of a method for predicting user behavior preferences based on user location according to an embodiment. As shown in fig. 1, the method comprises the steps of:
step S110: and obtaining personal position data corresponding to the target user, and screening at least one key position point corresponding to the target user according to the stay time and/or the stay frequency corresponding to each position point contained in the personal position data.
The personal location data corresponding to the target user is longitude and latitude data of each location point where the target user is located.
Specifically, it is determined whether the staying time duration corresponding to each location point included in the personal location data is greater than a preset time duration threshold, and/or whether the staying frequency corresponding to each location point included in the personal location data is greater than a preset frequency threshold. And if so, determining the position points contained in the personal position data as key position points corresponding to the target user. Wherein, the number of the key position points is at least one.
Step S120: and acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data.
The GIS data refers to data of a certain location point obtained from a geographic information system. Specifically, longitude and latitude data of the key position point are matched with longitude and latitude data in GIS data, and the GIS data successfully matched with the longitude and latitude data is determined as target GIS data corresponding to the key position point. Wherein, a certain GIS data contains at least one interest point. And determining interest points corresponding to the target GIS data according to the target GIS data corresponding to the key position points. The interest point refers to the landform, administrative division, regional function, business service area and the like near a certain position point in the geographic information system. It should be noted that successful matching of the longitude and latitude data means that an error between the longitude and latitude data of the key location point and the longitude and latitude data in the GIS data is within a preset error range.
Step S130: and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Specifically, the user behavior preference is presumed according to the type of the interest point corresponding to the target GIS data, the stay time and the stay time period corresponding to the interest point. For example, the type of the interest point is a cinema, the dwell time corresponding to the interest point is 3 hours, the dwell period is saturday afternoon, and the dwell frequency is 4 times per month, so that the target user can be presumed to be a movie lover and is accustomed to going to the cinema to watch movies on weekends. The user behavior preference is used for describing characteristics of preference, occupation, identity and the like of the user, and all contents related to the user behavior can be used as the user behavior preference. For example, the user behavior preferences in the present invention specifically include: behavioral preferences, and identity characteristics (e.g., occupation, etc.).
In conclusion, the method combines personal position data and GIS data, fully utilizes the GIS data to conduct diversified prediction, is not limited to a specific vertical field, and gets rid of dependence on large-scale crowd data sets.
Example two
Fig. 2 is a flowchart illustrating a method for predicting user behavior preferences based on user location according to a second embodiment. As shown in fig. 2, the method comprises the steps of:
step S210: and obtaining personal position data corresponding to the target user, and screening at least one key position point corresponding to the target user according to the stay time and/or the stay frequency corresponding to each position point contained in the personal position data.
The personal location data corresponding to the target user is longitude and latitude data of each location point where the target user is located. The personal location data may come from various sources, including but not limited to Global Positioning System (GPS), BeiDou Satellite Navigation System (BDS), and operator base station Positioning.
Specifically, the personal location data includes: slice location data corresponding to a plurality of time slices, respectively. For example, the personal location data is location information of each location point where the target user is located within 10 days, the time slice is preset to 1 day, and the personal location data is divided into 10 time slice corresponding slice location data. For example, the date of day 1 is 2/17/2019, and 2/17/2019 corresponds to one piece of location data.
In specific implementation, first, the stay time of each position point included in each piece of position data is determined, and position points with stay time longer than a preset time threshold are screened as candidate position points in the piece of position data. For example, fig. 5 shows an abstract diagram of a user location trajectory, and as shown in fig. 5, in the sliced location data corresponding to 2, 17 and 2019, the preset duration threshold is 0.5 hour. The residence time of the position point A was 1 hour and 3.3 hours, the residence time of the position point B was 3 hours and 4 hours, the residence time of the position point C was 1.5 hours, and the residence time of the position point D was 1 hour. The stay time of the position point A, B, C, D is longer than a preset time length threshold, and the position point A, B, C, D is screened as a candidate position point in the sliced position data. Further, the user position track under the time slice corresponding to the slice position data is determined according to the candidate position points in the slice position data.
Then, according to the occurrence frequency of each candidate position point in each fragment position data, determining the staying frequency of each candidate position point, and screening the candidate position points with the staying frequency not less than a preset frequency threshold value as key position points. Wherein, at least one of the screened key position points is selected. For example, the preset frequency threshold is the number of time slices, and in each piece of slice position data corresponding to 10 time slices, the number of times that the position point a appears is 10, the number of times that the position point B appears is 10, the number of times that the position point C appears is 9, and the number of times that the position point D appears is 10. The staying frequency of the position point A, B, D is not less than the preset frequency threshold value by 10 times, and the position point A, B, D is screened as a key position point corresponding to the target user. Further, determining a user coincidence track according to the key position points corresponding to the target user.
Step S220: and acquiring target GIS data corresponding to at least one key position point and interest points corresponding to the target GIS data.
The number of the key location points corresponding to the target user determined in step S210 may be one or more. GIS data refers to data of a certain location point obtained from a geographic information system.
Specifically, longitude and latitude data of the key position point are matched with longitude and latitude data in GIS data, and the GIS data successfully matched with the longitude and latitude data is determined as target GIS data corresponding to the key position point. Wherein, a certain GIS data contains at least one interest point. And determining interest points corresponding to the target GIS data according to the target GIS data corresponding to the key position points. The interest point refers to the landform, administrative division, regional function, business service area and the like near a certain position point in the geographic information system. It should be noted that successful matching of the longitude and latitude data means that an error between the longitude and latitude data of the key location point and the longitude and latitude data in the GIS data is within a preset error range.
Step S230: and screening the target interest points from a plurality of interest points corresponding to the target GIS data.
Specifically, the target interest points may be screened in at least one of the following four ways:
the first mode specifically includes: and when a plurality of interest points corresponding to certain target GIS data are available, judging whether each interest point is matched with a preset prediction target or not, and determining the interest point matched with the preset prediction target as a target interest point. For example, the preset prediction target is to infer occupation, income and hobbies of the target user. After obtaining a plurality of interest points corresponding to a certain target GIS data, the interest points not related to occupation, income and hobbies are screened out, for example, park type interest points are not related to occupation, income and hobbies, and park type interest points can be screened out.
The second mode specifically includes: when a plurality of interest points corresponding to certain target GIS data are available, calculating the distance between the interest points and the key position points, judging whether the distance between the interest points and the key position points meets a preset distance matching rule or not, and determining the interest points meeting the preset distance matching rule as target interest points. In specific implementation, when the longitude and latitude data of the key location point in step S220 cannot be completely matched with the longitude and latitude data in the GIS data, that is, when the longitude and latitude data of the key location point and the longitude and latitude data in the GIS data have an error within a preset error range, the distance between the interest point corresponding to the target GIS data and the key location point is calculated. For example, the preset distance matching rule is to determine the interest point with the shortest distance to the key position point as the target interest point. Fig. 7 shows a schematic diagram of the shortest distance matching, as shown in fig. 7, the distances between the points of interest a, b, c, d, e and the key position points are calculated, the point of interest with the shortest distance to the key position point is selected, and the point of interest with the shortest distance (i.e., the point of interest a) is determined as the target point of interest.
The third mode specifically includes: judging whether the attribute of the interest point meets a preset constant station attribute rule, and if the attribute of the interest point meets the preset constant station attribute rule, determining the interest point as a target interest point, wherein the preset constant station attribute rule specifically comprises the following steps: the stay time corresponding to the interest point is longer than a preset resident time threshold, and the stay time meets a preset resident time range. In specific implementation, the preset resident time threshold is 7 hours, and the preset resident time period ranges from 8 am to 8 pm. For example, the stay time corresponding to the restaurant type interest point a is 12 hours, the stay time is from 9 am to 9 pm, the restaurant type interest point a meets the preset permanent property rule, the restaurant type interest point a is determined as the target interest point, and the work of the target user in the restaurant can be presumed according to the restaurant type interest point a. It should be noted that, the present embodiment does not limit the specific meaning of the regular-premises attribute rule, and those skilled in the art may determine the specific meaning of the regular-premises attribute rule in other manners.
The fourth mode specifically includes: and when a plurality of interest points corresponding to certain target GIS data exist, judging whether the interest points have mutually contradictory logics, and if so, screening the target interest points according to the distance between the interest points and the key position points and the weight corresponding to the interest points. When a plurality of interest points corresponding to a certain target GIS data are provided, the weight corresponding to the interest points is preset. In specific implementation, for example, the type of the point of interest b is a high-income carrier, the type of the point of interest c is a low-income carrier, and the point of interest b and the point of interest c corresponding to a certain target GIS data are mutually contradictory. And comparing the distance between the interest point b and the key position point with the distance between the interest point c and the key position point, and eliminating the interest points with longer distances to eliminate mutually contradictory logics. If the distances between the interest points b and c and the key position points are the same, the weights of the interest points b and c are compared, and the interest points with lower weights are removed to eliminate mutually contradictory logics. In addition, when the points of interest corresponding to different key position points have mutually contradictory logics, the process can be repeated, the points of interest which are far away from the key position points and have light weight are removed, and finally the mutually contradictory logics are eliminated. It should be noted that the present embodiment does not limit the specific method for eliminating the mutually contradictory logic, and those skilled in the art may adopt other methods to eliminate the mutually contradictory logic between multiple points of interest.
Step S240: and predicting the user behavior preference of the target user according to the target interest points.
Specifically, the user behavior preference is presumed according to the type of the target interest point, the stay time and the stay time period corresponding to the target interest point. For example, the type of the target interest point is cinema, the dwell time corresponding to the target interest point is 3 hours, the dwell period is saturday afternoon, the dwell frequency is 4 times a month, and the target user can be presumed to be a movie fan and is accustomed to going to the cinema to watch movies on weekends.
In summary, the method combines personal location data and GIS data, and predicts the user behavior preference of the target user according to the consideration of multiple dimensions such as the distance between the interest point and the key location point, the weight of the interest point, the stay time of the target user and the like. The method has the advantages that the crowd data set under a certain scene is not relied on as a prediction basis, GIS data is fully utilized to conduct diversified prediction, and the data quality problem of the large-scale crowd data set is avoided.
The method of the present invention is described below in a specific example, which comprises the following steps:
the method comprises the following steps: and cleaning personal position data.
The method is characterized in that the position behavior of a person in the whole contract in a period of time is used for outlining the personal position behavior track, the outlining of the position behavior track can be realized by selectively combining with a GIS system, and can also be separated from the GIS system, the purpose of outlining the personal track in this stage is to extract effective information from mass personal position data, clear data with low information value in the position data, and extract key position data for use in subsequent steps. While the person's location behavior trajectory is being traced, the processing of the location data is accompanied by time dimension data, such as 6.5 hours of stay at the location of longitude LNG1, LAT1, at 17.00, 2.8.35, at 2.25.30, 2019, at2, LAT2, at 3 hours.
As shown in fig. 5, fig. 5 shows an abstract diagram of a user location track, and taking a day as an example for observing a location behavior track of a certain person as a period, the personal location data can be abstracted and abstracted into several important fixed points. Other redundant position data should be cleared away at the step of clearing personal position data, for example, a person goes to a company from home in the morning, position change data on the way does not help the refinement of personal key position data, and the data has the characteristics of rapid change of geographic position and short stay time of a single position. After cleaning redundant position data, abstracting out core position points A, B, C, D, recording the geographic coordinates of each core position and the time from other key positions to the current position, continuously monitoring the stay time of the target at the key position, and finally abstracting out a track according to the data recorded in the day.
Monitoring the daily position behavior data according to the above-mentioned method, accumulating the track data of multiple days, checking the coincidence degree, and further refining the key position points which repeatedly appear, as shown in fig. 6, wherein fig. 6 shows a key position point refining schematic diagram of the coincidence track. The trace points with less occurrence and low coincidence degree are eliminated and filtered, certain deviation threshold error correction can be given in the elimination process, the trace points can be considered as coincident within an error range, the overfitting phenomenon that the coincident is calculated only by absolute position matching is avoided, and the threshold can be specifically analyzed and adjusted according to specific conditions. According to specific conditions, the accumulated duration of the extracted key position information and the track period can be flexibly adjusted.
Step two: and cleaning the GIS data.
GIS data cleaning mainly comprises three main tasks:
filtering GIS data irrelevant to the key position.
The GIS data is filled with countless location points, each location point may correspond to a plurality of POIs (points of interest), and the POIs are entity objects in the GIS and are information in the GIS data which can be used for predicting behavior preference and identity characteristics. If the POI information of a certain location point is queried from the GIS each time and then processed, the efficiency is low, so GIS data should be preprocessed, and only the GIS data at the location point related to the step one should be considered. After the relevant GIS data is obtained, the POI at the position point is filtered according to the predicted target, the POI irrelevant to the predicted target needs to be removed, and the data size is further reduced, for example: if someone goes to the park, which is a behavior that does not help the intended predicted target, then no POIs such as "park" should appear in the processed GIS data.
And secondly, carrying out weight division on the condition that multiple POIs exist in the same position.
The same position may have multiple POI attributes, and a weight division method is needed to rank the POI attributes reflected by the position and assign appropriate weights. A more straightforward way is to weight the traffic estimates of the services provided by the POI, i.e. services with more traffic will have a higher probability of being used than services with less traffic, and therefore be given a higher weight.
And extracting behavior preference and identity characteristics behind the POI.
The goal of prediction is to identify the behavioral preferences and identity characteristics of an individual, for which we need to extract the meaning behind the POI. The conversion of the POI information into behavior preference and identity feature can be simply manually labeled or extracted from the relevant data of the POI by using a natural language processing method.
After the GIS data is cleaned and mined, the GIS data which is simplified, has weight distribution and is described by behavior preference and identity characteristics is obtained.
Step three: and fusing personal position data and GIS data for judgment and prediction.
After obtaining personal core track position data and cleaning and mining GIS data, behavior preference and identity characteristic prediction can be carried out by combining the personal core track position data and the cleaning and mining GIS data, through the preparation of the two steps, the prediction process is actually converted into a process for extracting corresponding GIS data according to a core position track, and the core problem to be solved in the process is how to distribute the GIS data to the position under the condition that the position data cannot be directly corresponding to interest points in the GIS data.
A simple and easy-to-use algorithm is to use distance calculation, take the feature of the interest point having the shortest distance to the target position in the GIS data as the feature of the target position, and take the distance as the position weight, and bring it into the output result, so as to optimize the prediction result in the subsequent steps, as shown in fig. 7, fig. 7 shows a shortest distance matching diagram.
Step four: and (5) correcting the pre-output data.
The pre-output data modification process can be divided into two categories:
the logic correction processing of the ordinary residence (working place and residence place) is carried out.
According to the trajectory data, a personal ordinary residence (working place and residential place) is predicted from the aspects of time and space, and whether a certain key position on the personal trajectory is the ordinary residence or not is judged from the pre-output data by integrating a plurality of factors such as the stay time of the position, the appearance time period of the position, the deviation between the positions, the environment reflected by the position on the GIS and the like. For such data, the regular premises attribute will be treated in a manner that is stronger than any other attribute. For example: individuals often appear at two points a and B, a and B are identified as a workplace and a place of residence, respectively, and point a is a restaurant, then for location a, attributes of the workplace should be prioritized, the predicted target has the traits of "practioners" and should not be identified as "liking the restaurant", and similarly, if there is a senior residential district near point B, there is a movie theater, location B should be prioritized for attributes of the place of residence, match the senior residential district, be identified as "high income people", and should not be identified as "movie fans", even though the weight of "movie fans" is greater than "high income people" in the pre-output data of the previous step.
② paradox logic correction processing.
After behavior preferences of the target are made based on the pre-output data and the identity characteristics are determined, whether the behavior preferences and the characteristics are mutually contradictory or not should be checked, and if the behavior preferences and the characteristics are mutually contradictory, correction processing is required. The simplest way is to remove violation decisions where the probability is lower, thereby eliminating paradoxical logic. However, a better method is to preferentially select a position with a lower weight (lower matching degree and longer distance) in the pre-output data to modify the position when two behavior preferences contradict identity characteristic determination, modify the position into a behavior preference and an identity characteristic attribute (next-level POI) with a lower weight at the position in the GIS data, check the mutual paradox condition again, and repeat the behaviors again if the mutual paradox still exists until the paradox logic does not exist any more.
The extreme case is that after all new behavior preferences and identity characteristic attributes are iterated, mutual contradiction still exists, at this time, the position with higher position weight in the pre-output data can be modified instead, the behaviors are repeated, if the mutual contradiction problem cannot be solved after the attempt, the position characteristic data with lower position weight is removed, and mutual contradiction logic is eliminated. And obtaining final judgment data after finishing the correction processing. Detailed description of the preferred embodimentsfigure 8 illustrates a flowchart of the mutually contradictory determination correction process shown in fig. 8. The position track a is a key position point, and the position track B is a key position point. First, the distance between the POI interest point corresponding to the position trajectory a and the position trajectory a is compared with the distance between the POI interest point corresponding to the position trajectory B and the position trajectory B. The distance between the POI interest point corresponding to the position track a and the position track a is short, that is, the position weight of the POI interest point corresponding to the position track a is low, and the POI interest point corresponding to the position track a is modified to eliminate the mutually contradictory logics. Then, the weights of a plurality of POI interest points corresponding to the position track A are compared, and the POI interest points are sequentially modified from low to high according to the weights of the POI interest points, so that the mutually contradictory logics are eliminated finally.
Therefore, the personal behavior preference and identity feature prediction is not made based on the crowd data set in a certain scene, but made through the feature embodied in the GIS system based on the prediction target. The method has the advantages that the starting point of prediction is personal behaviors, behavior preference and identity characteristic judgment and prediction are performed by combining GIS data, a crowd data set under a certain scene is not relied on as a prediction basis, the prediction is not entangled in details of a specific field, and diversified prediction is performed at a higher level. Because GIS data is not limited to a specific vertical field, behavior preference prediction is free from the limitation that a specific scene needs to be relied on in the prior art, and meanwhile, because the problems that a huge crowd data set is needed as a basis or the data set is too sparse and the like do not exist, the problems of the prior art in data scale and data quality are avoided. In general, compared with the traditional method, the method disclosed by the invention gets rid of the constraint of taking the crowd data set as a prediction basis, and has the characteristic of diversification in the prediction direction.
EXAMPLE III
Fig. 3 is a block diagram of an apparatus for predicting user behavior preference based on user location according to a third embodiment, the apparatus comprising:
the key position point screening module 31 is adapted to acquire personal position data corresponding to a target user, and screen at least one key position point corresponding to the target user according to the stay duration and/or the stay frequency corresponding to each position point included in the personal position data;
a GIS data and interest point acquisition module 32 adapted to acquire target GIS data corresponding to the at least one key location point and interest points corresponding to the target GIS data;
and the behavior preference prediction module 33 is adapted to predict the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
Optionally, the personal location data comprises: slice position data corresponding to a plurality of time slices, respectively;
the key location point screening module 31 is adapted to:
determining the stay time of each position point contained in each fragment position data, and screening the position points with the stay time longer than a preset time threshold value as candidate position points in the fragment position data;
and determining the staying frequency of each candidate position point according to the occurrence frequency of each candidate position point in each fragment position data, and screening the candidate position points with the staying frequency not less than a preset frequency threshold value as key position points.
Optionally, the behaviour preference prediction module 33 is adapted to:
when a plurality of interest points corresponding to the target GIS data are available, judging whether each interest point is matched with a preset prediction target or not;
and determining the interest points matched with the preset prediction target as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behaviour preference prediction module 33 is adapted to:
when a plurality of interest points corresponding to the target GIS data are available, calculating the distance between each interest point and the key position point;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule or not;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behaviour preference prediction module 33 is adapted to:
when a plurality of interest points corresponding to the target GIS data exist, judging whether the attributes of the interest points meet preset constant station attribute rules or not;
if yes, the interest point is determined as a target interest point, and the user behavior preference of the target user is predicted according to the target interest point.
Optionally, the behaviour preference prediction module 33 is adapted to:
when a plurality of interest points corresponding to the target GIS data exist, judging whether mutually contradictory logics exist among the interest points;
if yes, screening the target interest points according to the distance between the interest points and the key position points and the weight corresponding to the interest points, and predicting the user behavior preference of the target user according to the target interest points.
Optionally, the behaviour preference prediction module 33 is adapted to:
and presetting the weight corresponding to the interest point according to the pedestrian volume corresponding to the interest point and/or the distance between the interest point and the key position point.
Embodiments of the present application provide a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction may execute a method for predicting user behavior preference based on a user location in any of the above method embodiments.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the electronic device.
As shown in fig. 4, the electronic device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein:
the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408.
A communication interface 404 for communicating with network elements of other devices, such as clients or other servers.
The processor 402 is configured to execute the program 410, and may specifically execute relevant steps in the above-described embodiment of the fault location method based on multiple levels of network nodes.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The electronic device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may be specifically configured to cause the processor 402 to perform the operations in the above-described method embodiments.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in a system according to embodiments of the present invention. The present invention may also be embodied as apparatus or system programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several systems, several of these systems may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A method of predicting user behavior preferences based on user location, comprising:
acquiring personal position data corresponding to a target user, and screening at least one key position point corresponding to the target user according to the stay time length and/or stay frequency corresponding to each position point contained in the personal position data;
acquiring target GIS data corresponding to the at least one key position point and interest points corresponding to the target GIS data;
and predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
2. The method of claim 1, wherein the personal location data comprises: slice position data corresponding to a plurality of time slices, respectively;
the screening, according to the stay duration and/or the stay frequency corresponding to each location point included in the personal location data, at least one key location point corresponding to the target user includes:
determining the stay time of each position point contained in each fragment position data, and screening the position points with the stay time longer than a preset time threshold value as candidate position points in the fragment position data;
and determining the staying frequency of each candidate position point according to the occurrence frequency of each candidate position point in each fragment position data, and screening the candidate position points with the staying frequency not less than a preset frequency threshold value as the key position points.
3. The method of claim 1, wherein the predicting user behavior preferences of the target user from the points of interest corresponding to the target GIS data comprises:
when a plurality of interest points corresponding to the target GIS data are available, judging whether each interest point is matched with a preset prediction target;
and determining the interest points matched with the preset prediction target as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
4. The method of claim 1, wherein the predicting user behavior preferences of the target user from the points of interest corresponding to the target GIS data comprises:
when a plurality of interest points corresponding to the target GIS data are available, calculating the distance between the interest points and the key position points;
judging whether the distance between the interest point and the key position point meets a preset distance matching rule or not;
and determining the interest points meeting the preset distance matching rule as target interest points, and predicting the user behavior preference of the target user according to the target interest points.
5. The method of claim 1, wherein the predicting user behavior preferences of the target user from the points of interest corresponding to the target GIS data comprises:
when a plurality of interest points corresponding to the target GIS data exist, judging whether the attributes of the interest points meet preset permanent location attribute rules or not;
if yes, determining the interest point as a target interest point, and predicting the user behavior preference of the target user according to the target interest point.
6. The method of claim 1, wherein the predicting user behavior preferences of the target user from the points of interest corresponding to the target GIS data comprises:
when a plurality of interest points corresponding to the target GIS data exist, judging whether mutually contradictory logics exist among the interest points;
if yes, screening target interest points according to the distance between the interest points and the key position points and the weight corresponding to the interest points, and predicting user behavior preference of the target user according to the target interest points.
7. The method of claim 6, wherein when there are a plurality of points of interest corresponding to the target GIS data, before determining whether there is mutually contradictory logic between the points of interest, further comprising:
and presetting the weight corresponding to the interest point according to the pedestrian volume corresponding to the interest point and/or the distance between the interest point and the key position point.
8. An apparatus to predict user behavior preferences based on user location, comprising:
the key position point screening module is suitable for acquiring personal position data corresponding to a target user and screening at least one key position point corresponding to the target user according to the stay time length and/or the stay frequency corresponding to each position point contained in the personal position data;
the GIS data and interest point acquisition module is suitable for acquiring target GIS data corresponding to the at least one key position point and interest points corresponding to the target GIS data;
and the behavior preference prediction module is suitable for predicting the user behavior preference of the target user according to the interest points corresponding to the target GIS data.
9. An electronic device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to a method of predicting user behavior preferences based on user location as recited in any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to a method of predicting user behavior preferences based on user location as recited in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635221.9A CN112232845B (en) | 2019-07-15 | 2019-07-15 | Method and device for predicting user behavior preference based on user position |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635221.9A CN112232845B (en) | 2019-07-15 | 2019-07-15 | Method and device for predicting user behavior preference based on user position |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112232845A true CN112232845A (en) | 2021-01-15 |
| CN112232845B CN112232845B (en) | 2023-12-19 |
Family
ID=74111085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910635221.9A Active CN112232845B (en) | 2019-07-15 | 2019-07-15 | Method and device for predicting user behavior preference based on user position |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112232845B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150148076A1 (en) * | 2013-04-02 | 2015-05-28 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Push method, system and server based on location information |
| US20150204685A1 (en) * | 2014-01-22 | 2015-07-23 | Mapquest, Inc. | Methods and systems for providing dynamic point of interest information and trip planning |
| CN105740347A (en) * | 2016-01-25 | 2016-07-06 | 四川长虹电器股份有限公司 | GPS based user information acquisition and behavior analysis method |
| CN106844376A (en) * | 2015-12-03 | 2017-06-13 | 高德软件有限公司 | Recommend the method and device of point of interest |
| US20170241788A1 (en) * | 2016-02-22 | 2017-08-24 | Bayerische Motoren Werke Aktiengesellschaft | Method and System for Contextually Recommending a Place of Interest to a User and Smart Check-In |
| CN107515949A (en) * | 2017-09-14 | 2017-12-26 | 云南大学 | User's space-time method for measuring similarity in interest point prediction and recommendation |
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN109460509A (en) * | 2018-10-12 | 2019-03-12 | 平安科技（深圳）有限公司 | User interest point appraisal procedure, device, computer equipment and storage medium |
| CN109635190A (en) * | 2018-11-28 | 2019-04-16 | 四川亨通网智科技有限公司 | User characteristics method for digging based on position and behavior Conjoint Analysis |
| CN109635070A (en) * | 2019-01-18 | 2019-04-16 | 上海图趣信息科技有限公司 | A kind of method and its data-updating method based on movement track building user interest portrait |
-
2019
- 2019-07-15 CN CN201910635221.9A patent/CN112232845B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150148076A1 (en) * | 2013-04-02 | 2015-05-28 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Push method, system and server based on location information |
| US20150204685A1 (en) * | 2014-01-22 | 2015-07-23 | Mapquest, Inc. | Methods and systems for providing dynamic point of interest information and trip planning |
| CN106844376A (en) * | 2015-12-03 | 2017-06-13 | 高德软件有限公司 | Recommend the method and device of point of interest |
| CN105740347A (en) * | 2016-01-25 | 2016-07-06 | 四川长虹电器股份有限公司 | GPS based user information acquisition and behavior analysis method |
| US20170241788A1 (en) * | 2016-02-22 | 2017-08-24 | Bayerische Motoren Werke Aktiengesellschaft | Method and System for Contextually Recommending a Place of Interest to a User and Smart Check-In |
| CN107515949A (en) * | 2017-09-14 | 2017-12-26 | 云南大学 | User's space-time method for measuring similarity in interest point prediction and recommendation |
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN109460509A (en) * | 2018-10-12 | 2019-03-12 | 平安科技（深圳）有限公司 | User interest point appraisal procedure, device, computer equipment and storage medium |
| CN109635190A (en) * | 2018-11-28 | 2019-04-16 | 四川亨通网智科技有限公司 | User characteristics method for digging based on position and behavior Conjoint Analysis |
| CN109635070A (en) * | 2019-01-18 | 2019-04-16 | 上海图趣信息科技有限公司 | A kind of method and its data-updating method based on movement track building user interest portrait |
Non-Patent Citations (2)
| Title |
|---|
| 周洋: ""基于智能手机的个体出行模式识别研究"", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 4, pages 034 - 914 * |
| 徐以彬: ""基于GPS数据的用户轨迹挖掘与预测研究"", 《中国优秀硕士学位论文全文数据库基础科学辑》, no. 3, pages 008 - 88 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112232845B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9183497B2 (en) | Performance-efficient system for predicting user activities based on time-related features | |
| CN107291888B (en) | Machine learning statistical model-based living recommendation system method near living hotel | |
| CN107798412B (en) | Route recommendation method and device | |
| US8612134B2 (en) | Mining correlation between locations using location history | |
| Chen et al. | Constructing and comparing user mobility profiles | |
| CN110334289B (en) | Travel destination determining method and target user determining method | |
| CN111949834A (en) | Site selection method and site selection platform | |
| CN105260466A (en) | Picture pushing method and apparatus | |
| EP3739470A1 (en) | Method and apparatus for performing categorised matching of videos, and selection engine | |
| JP2018077821A (en) | Method, program, server device, and processor for generating predictive model of category of venue visited by user | |
| CN112214677A (en) | Interest point recommendation method and device, electronic equipment and storage medium | |
| CN110262863B (en) | Method and device for displaying terminal main interface | |
| CN109918048B (en) | Target object extraction method, device and system and computer readable storage medium | |
| CN111563560A (en) | Data stream classification method and device based on time sequence feature learning | |
| CN111597447A (en) | Object pushing method and device, electronic equipment and storage medium | |
| CN113742580A (en) | Target type data recall method and device, electronic equipment and storage medium | |
| CN115774819B (en) | Point of interest recommendation method and system based on hierarchical cyclic neural network | |
| US11300418B2 (en) | Customized trip grouping based on individualized user preferences | |
| CN110851742A (en) | Interest point recommendation method and device based on position and time information | |
| CN112232845A (en) | Method and device for predicting user behavior preference based on user position | |
| US11050834B1 (en) | Method for automatically assigning visits to partially observable location data streams | |
| CN111242723B (en) | User child and child condition judgment method, server and computer readable storage medium | |
| EP1388824A2 (en) | Communication terminal and information processing apparatus of a payment system | |
| CN108694625A (en) | Equity preference predictor method, device and server | |
| US9532165B2 (en) | Method and apparatus for location prediction using short text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |